The paper explores learning good policies from past data in large state spaces.
problem Learning good policies from historical data in large state spaces.
method Introduces expressivity assumptions and data coverage for function approximation and algorithmic design.
result A variety of algorithms and their guarantees are presented based on assumptions and desired complexity.
A framework to quantify deployment risk in ML systems, especially for rare states.
problem Under-supported rare states in ML models lead to unreliable performance in unseen data.
method Blind-Spot Mass (B_n(tau)) using Good-Turing unseen-species estimation.
result Identifies and quantifies the risk of under-supported states in ML models.
Paper introduces a new framework to improve sample efficiency in POMDPs learning.
problem Challenges in off-policy evaluation for POMDPs, especially with hidden states.
method Exploits the metric structure of belief space to relax coverage assumptions.
result Unified analysis technique yields tighter error bounds and sample efficiency improvements.
New method uses entropy to improve policy gradient exploration.
problem Limited exploration in policy gradient methods.
method Entropy regularization with discounted future state distribution.
result Proves convergence to locally optimal policy.
New insights show coverage conditions are crucial for efficient online reinforcement learning.
problem The role of coverage conditions in determining sample complexity of offline reinforcement learning.
method Established a connection between coverage conditions and sample efficiency in online reinforcement learning.
result Coverability, a structural property of MDPs, enables sample-efficient exploration in online reinforcement learning.
New L1-Coverage objective simplifies exploration in reinforcement learning.
problem Challenges in exploration for high-dimensional domains.
method Introduces L1-Coverage objective to enable efficient exploration and planning. result First computationally efficient algorithms for online reinforcement learning with low coverability.
EDL discovers state-covering skills without relying on task rewards.
problem Discovering skills in reinforcement learning without a task-oriented reward function.
method EDL optimizes information-theoretic objective using different machinery to address coverage problem.
result EDL discovers state-covering skills more effectively than existing methods.
This paper introduces CENIE to quantify environment novelty for better UED.
problem Challenges in measuring environment novelty for effective UED.
method CENIE framework using state-action space coverage and Gaussian Mixture Models.
result CENIE improves UED performance across multiple benchmarks.
Study on future-dependent value functions for off-policy evaluation in complex environments.
problem Exponential dependence on horizon in off-policy evaluation for complex observations.
method Developed novel coverage assumptions for POMDPs to achieve polynomial bounds.
result Achieved polynomial bounds on previously exponential quantities, improving off-policy evaluation.
Offline RL struggles with sample efficiency due to fundamental barriers.
problem Sample efficiency in offline RL with value function approximation.
method Analyzes the necessity of distributional and representational assumptions.
result Even with concentrability and realizability, sample complexity is polynomial in state space size.
Paper tackles covariate shift in offline IL using less proficient behavior data.
problem Mitigating covariate shift in Imitation Learning with limited data coverage.
method Model-based IL from Offline Data (MILO) framework.
result MILO can combat covariate shift even with sub-optimal behavior policy data.
CADD improves generative quality by augmenting discrete diffusion with continuous latent space.
problem Loss of semantic information between denoising steps in discrete diffusion models.
method Introduces a framework that augments discrete state space with a continuous latent space, allowing for graded, informative masked tokens.
result CADD improves generative quality across text generation, image synthesis, and code modeling.
Continuous control tasks in reinforcement learning are important because they provide an important framework for learning in high-dimensional state spaces with deceptive rewards, where the agent can easily become trapped into suboptimal solutions. One way to avoid local optima is to use a population of agents to ensure…
Paper proposes a new method for conditional coverage in conformal prediction.
problem Lack of strong conditional coverage guarantees in existing conformal prediction methods.
method Modified non-conformity score using local approximation of conditional distribution.
result Unified framework and empirical evaluations show advantage of the new method.
This work introduces COLA, a strategy to aggregate conformal prediction sets efficiently.
problem Efficiently combining multiple conformity scores to reduce prediction set size.
method Introduces COnfidence-Level Allocation (COLA) to optimally allocate confidence levels across sets.
result COLA achieves smaller prediction sets than state-of-the-art methods while maintaining valid coverage.
This work improves policy optimization by maximizing entropy of state distribution, leading to better exploration.
problem Lack of exploration in state space when maximizing policy entropy.
method Proposes maximizing the entropy of a lower bound approximation to the state weighting distribution, based on latent space representation.
result Entropy regularization based on marginal state distribution achieves superior state space coverage and better performance in various domains.
The paper derives uniform stability-based coverage bounds for conformal prediction methods.
problem Establishing theoretical guarantees for conformal prediction methods.
method Uniform stability perspective applied to full-conformal, jackknife+, and CV+ prediction regions.
result Coverage bounds for finite-dimensional models derived using a concentration argument.
SA-BCP combines long-term and local evidence for efficient, adaptive online prediction.
problem Balancing fast adaptation and stable coverage in online prediction.
method State-Adaptive Bayesian Conformal Prediction (SA-BCP) using gated convex combination of temporal inertia and spatial evidence.
result SA-BCP achieves at-or-above-nominal coverage with substantially sharper intervals compared to discounted Bayesian CP.
The paper improves prediction intervals for non-parametric regression using histograms.
problem Computing accurate prediction intervals for non-parametric regression models.
method Uses conditional histograms to estimate conditional distributions and compute shortest prediction intervals.
result The method provides prediction intervals with provable marginal coverage and asymptotic conditional coverage.
LPCI provides valid prediction intervals for longitudinal data.
problem Current conformal prediction methods for time series data lack cross-sectional coverage when applied to longitudinal datasets.
method Modeling residual data as a quantile fixed-effects regression problem, constructing prediction intervals with a trained quantile regressor.
result LPCI achieves valid cross-sectional coverage and outperforms existing benchmarks in terms of longitudinal coverage rates.
A new method for online prediction uncertainty quantification in non-exchangeable panel data.
problem Challenges in quantifying predictive uncertainty for non-exchangeable panel data.
method Online conformal prediction framework for non-exchangeable panel data, using similarity weights and adaptive miscoverage levels.
result Improves coverage on worst-covered target units through adaptive interval-width allocation.
This paper tackles hidden state inference for HMMs using particle filtering.
problem Inference for hidden states under HMMs is challenging due to unavailable true labels.
method Adaptive conformal inference framework using particle filtering.
result The framework produces prediction sets with specific aggregated coverage levels.
Two conformal methods create flexible conditional predictive bands without strong assumptions.
problem Achieving asymptotic conditional coverage without strong dependence assumptions.
method Flexible distribution-free conditional predictive bands using density estimators.
result Methods achieve better control of conditional coverage and smaller length than previous methods.
Metric learning enhances combinatorial coverage metrics' ability to predict classification errors.
problem Dataset dependence of combinatorial coverage metrics in anticipating classification errors.
method Metric learning to improve latent space separation of data classes.
result Metric learning increases SDCCMs' ability to distinguish between correctly and incorrectly classified data.
Paper tackles efficient exploration of unseen graph-structured environments.
problem Efficient exploration of unseen graph-structured environments.
method Learning to explore framework using reinforcement learning and graph-structured memory.
result Approach outperforms hand-engineered methods in software testing and real-world applications.
CTI produces efficient prediction intervals with guaranteed coverage.
problem Efficient and reliable uncertainty quantification in regression.
method CTI estimates conditional density for interval length, then thresholds intervals based on this density.
result CTI achieves smaller prediction sets with guaranteed coverage compared to existing methods.
New algorithm fills gaps in offline data for hybrid RL, achieving similar gains without coverage assumptions.
problem Lack of provable benefits in hybrid RL with coverage assumptions.
method Warm-starting optimistic online algorithms with offline data in experience replay buffer.
result Hybrid RL gains similar to offline-only RL without coverage assumptions, demonstrating efficient exploration.
CPATTA uses conformal prediction for efficient test-time adaptation.
problem Low data selection efficiency in existing ATTA methods.
method Conformal Prediction, online weight-update algorithm, domain-shift detector, staged update scheme.
result CPATTA consistently outperforms state-of-the-art methods by 5% in accuracy.
Paper bounds PAC RL sample complexity in deterministic MDPs.
problem Identify ε-optimal policy with high probability.
method Proposes nearly matching upper and lower bounds on sample complexity, introduces deterministic return gap, uses graph-theoretical concepts and maximum-coverage exploration.
result First nearly matching upper and lower bounds on sample complexity for PAC RL in deterministic MDPs.
This paper studies the trade-off between model accuracy and coverage for diagnosis models used by patients.
problem Balancing accuracy and coverage in diagnosis models for patient use.
method Learned diagnosis models with varying coverage from EHR data.
result A 1% drop in top-3 accuracy for every 10 diseases added to the coverage.
C-SymmPI provides near-conditional coverage for structured data with group symmetries.
problem Establishing near-conditional coverage guarantees for structured data with group symmetries.
method Developed a framework C-SymmPI that achieves near-conditional coverage under general data structures with group symmetries.
result Near-conditional coverage guarantees for structured data with group symmetries.
Novel method for time-series prediction with tighter confidence intervals.
problem Improving prediction intervals for time-series data.
method Kernel-based Optimally Weighted Conformal Prediction Intervals (KOWCPI) using adaptive weights.
result KOWCPI achieves narrower confidence intervals with guaranteed coverage.
A new method for selective classification trades off accuracy for coverage.
problem Selective classification allows a classifier to abstain from predicting some instances.
method Optimizes a collection of class-wise decoupled one-sided empirical risks.
result The method achieves near-optimal coverage in high target accuracy regimes.
Improved local explainer aggregation for interpretable machine learning models.
problem Improving the interpretability of black box machine learning models.
method Non-convex optimization and integer optimization framework for local explainer aggregation.
result Our method outperforms existing methods in terms of coverage and fidelity, particularly in multi-class settings.
Study uses TV news to measure climate risks affecting clean energy firms.
problem Understanding how climate risks impact clean energy firms' financial stability.
method Developed climate risk measures from TV news coverage and analyzed their effects on clean energy firms' risks.
result Increased TV news coverage of climate risks correlates with higher systematic risk and lower idiosyncratic risk for clean energy firms.
Examines WENDy-IRLS algorithm's noise robustness and efficiency in various differential equations.
problem Noise robustness and efficiency of WENDy-IRLS algorithm.
method Studied coverage and bias properties of WENDy-IRLS algorithm's estimators in various differential equations and noise distributions.
result WENDy-IRLS algorithm shows notable noise robustness and computational efficiency.
Develop a framework to evaluate the reliability of probabilistic emulation of physical systems.
problem Evaluating the reliability of probabilistic forecasts in physical systems.
method Developing a framework to assess the reliability of probabilistic emulation across diverse 2D spatiotemporal systems.
result CRPS-trained ensembles achieve more reliable uncertainties on single-step prediction and autoregressive rollouts.
New sampling bounds improve uniform coverage verification in machine learning.
problem Conservative bounds in classical coverage analyses at small failure probabilities.
method Variance-based analysis of uniform random sampling on a d-dimensional unit hypercube. result Sample complexity bound with logarithmic dependence on failure probability.
VAEBM combines VAEs and EBMs for efficient image generation.
problem Sampling from EBMs is slow and VAEs generate blurry images.
method VAEBM uses a VAE for quick sampling and an EBM to refine and exclude non-data regions.
result VAEBM generates high-quality images with short MCMC chains.
BCRL learns a Bellman complete representation for offline RL policy evaluation.
problem Learning a Q-function efficiently from offline data.
method BCRL learns a linear Bellman complete representation directly from data, enabling efficient OPE.
result BCRL achieves competitive OPE error and outperforms FQE in certain scenarios.
Extends conformal prediction to contrastive learning for better coverage of positive samples.
problem Lack of principled guarantees on coverage in contrastive learning.
method Introduces minimum-volume covering sets with learnable constraints.
result Improves inclusion-exclusion trade-offs in positive and negative samples.
New method uses label-weighted conformal prediction for macro-coverage guarantees in classification.
problem Finding a balance between class-conditional and marginal coverage in long-tailed datasets.
method Label-weighted conformal prediction for macro-coverage guarantees.
result Validated prediction sets with macro-coverage guarantees on large-scale image datasets.
New RL approach uses future state and action visitation measures for better exploration.
problem Improving exploration in reinforcement learning.
method Intrinsic reward based on future state and action visitation measures, using contraction operators.
result Policies achieve good state-action space coverage and high performance.
PersonalizedUS assesses breast cancer risk with local coverage guarantees.
problem Manual BI-RADS scoring leads to unnecessary biopsies and mental health burden.
method Conformal prediction for precise, personalized risk estimates.
result Local coverage guarantees with high sensitivity and specificity.
A new method for active learning works well across all label budgets.
problem Active learning methods perform poorly in both low and high label budgets.
method Uncertainty Herding: a simple, computationally fast method that optimizes uncertainty coverage.
result Uncertainty Herding nearly optimizes distribution-level coverage and performs well across various active learning tasks.
VSPS creates flexible prediction regions for multi-target regression with guaranteed coverage.
problem Uncertainty quantification in multi-target regression with complex distributions.
method Conditional normalizing flows with conformal calibration to identify dense regions.
result VSPS produces smaller, more informative prediction regions with robust coverage guarantees.
CoCP optimizes prediction intervals by jointly learning center and radius, improving efficiency and coverage.
problem Inefficient conformal prediction intervals under heteroscedasticity and skewness.
method Co-optimization framework that learns center and radius through alternating optimization steps.
result CoCP yields consistently shorter intervals and state-of-the-art conditional coverage diagnostics.
Binary linear classifiers are the most explainable up to negligible sets.
problem Measuring the explainability of machine learning classifiers.
method Introducing pointwise coverage to measure explainability and proving the binary linear classifier is the most explainable up to negligible sets.
result The binary linear classifier is uniquely the most explainable classifier up to negligible sets.